get_transcription

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations supplied, the description carries the full behavioral burden. "Read" implies non-mutating, but it never discloses whether the response is a job status, a partial result, or the final transcript, nor what happens for an unknown or expired ID, nor whether the caller must retry while the job is pending.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence with zero filler, and the scope word "existing" appears early. It is arguably too terse for a tool with no annotations, but nothing is redundant or buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a lookup tool with no annotations and no output schema, the description is thin: it does not say what a caller receives (status vs. transcript), whether results are eventually consistent, or how to recover from a missing ID. One sentence does not cover the behavioral surface an agent needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% for the single required parameter, so the description must add meaning. It does clarify that transcription_id is a *remote* transcription ID (not a local job handle), which is genuinely useful, but it gives no format, source, or where to obtain one.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ("Read") and resource ("existing transcription job/result") plus the lookup key ("remote transcription ID"). The read-by-ID pattern distinguishes it from transcribe_audio, but the description never names that sibling or any other, so differentiation is left to the reader.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use guidance, no prerequisites, no alternatives. The reader must infer that this is the polling/retrieval counterpart to transcribe_audio purely from the word "existing", with nothing stating when to call it versus transcribe_audio or get_generation_history_item.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.